def main():
"""
Main script.
NOTE: as a future extension, consider one trainer for each congressional
body. How do senators, reps tweet?
"""
DB = sqlite3.connect("data/tweets")
CLASSIFIER = NBClassifier()
# Train the classifier using sample of legislators' tweets.
r_limit = int(0.3 * 188331)
training_set = partition_sample(r_limit, DB, 'r')
for row in training_set:
CLASSIFIER.train(row)
# Now attempt to classify tweets in test set.
test_classifier(CLASSIFIER, DB, 'reps')
s_limit = int(0.3 * 29463)
training_set = partition_sample(r_limit, DB, 'd')
for row in training_set:
CLASSIFIER.train(row)
# Same thing for senators.
test_classifier(CLASSIFIER, DB, 'sens')
def main():
"""
Main script.
NOTE: as a future extension, consider one trainer for each congressional
body. How do senators, reps tweet?
"""
DB = sqlite3.connect("data/tweets")
REP_CLASSIFIER = NBClassifier()
# Train the classifier using sample of legislators' tweets.
r_limit = int(0.2 * 110000)
training_set = partition_sample(r_limit, DB, 'r')
for row in training_set:
REP_CLASSIFIER.train(row)
# Print 10 most common features in classifier, along with class info.
print "\nMOST COMMON REP FEATURES:\n"
REP_CLASSIFIER.print_common_features(n=20)
# Test the classifier.
test_classifier(REP_CLASSIFIER, DB, 'reps')
SEN_CLASSIFIER = NBClassifier()
s_limit = int(0.2 * 29463)
training_set = partition_sample(s_limit, DB, 's')
for row in training_set:
SEN_CLASSIFIER.train(row)
print "\nMOST COMMON SEN FEATURES:\n"
SEN_CLASSIFIER.print_common_features(n=20)
# Test the classifier.
test_classifier(SEN_CLASSIFIER, DB, 'sens')
